JP2003256809A - Image processor and image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To propose an image processor resistant to a noise by efficiently recognizing an electronic component having luminous parts other than a lead part even when any luminous part exists in the background by a common algorithm. <P>SOLUTION: In this image processor having an image pickup means 5 for imaging an electronic component 1, a model shape information storing part 8 for storing the model shape information of the electronic component 1 and image processing means 7a and 7b for processing the image signal of the electronic component 1 obtained by the image pickup means 5, the image processing means 7a and 7b compare the model position information of a plurality of feature points related with the model-shaped electronic component 1 outputted by the model shape information storing means 8 with the position information of a plurality of feature point candidates obtained by the picture signal, and select the combination of the feature point candidates which are the closest to the relative position relation of the feature points, and calculate the central position of the electronic component from the position information of the selected combination of the feature point candidates. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus and a processing method necessary for correcting the position of an electronic component such as an industrial robot or a component mounter for mounting an electronic component on a printed circuit board.

[0002]

2. Description of the Related Art Conventionally, an image pickup device such as a CCD camera has been used to correct the position of a component such as an industrial robot or a component mounter for mounting an electronic component (hereinafter, also referred to as "component") on a printed circuit board. The position of a component is detected by visually recognizing the component, and the position and angle of the component are corrected based on the detected component position information.

In such image recognition of an electronic component, an image signal of the electronic component is binarized to obtain a black and white image, and the white portion of the black and white image is used as an electrode (hereinafter referred to as "lead"). (Also referred to as "), the position of the component is calculated by regarding it as a reflection portion due to reflection illumination or the like. For example, by providing an edge checker or the like that detects a brightness change point by scanning the white part on the image signal obtained from the target electronic component, the position of this edge checker can be changed according to the shape of the electronic component to be detected. The brightness change point of the white part is determined and detected.

For example, in Japanese Patent No. 3225067, a camera is used to detect a luminance signal of an electrode (hereinafter, also referred to as "lead") on a scanning line of an image signal, and a signal obtained by differentiating the luminance signal is changed in brightness. A method for detecting a point to obtain the center position of the edge of the lead and calculating the distance or angle between the leads is described.

The patent No. 3 is shown in FIGS. 11 (a), 11 (b) and 11 (c).
A method for detecting electrodes of the component described in Japanese Patent No. 225067 will be described. FIG. 11A shows how a luminance signal is detected by the horizontal scanning line signal SX on the image signal for, for example, three leads 90 having a flaw 90d. 90L and 90R represent the left and right edges of the lead 90, respectively.

FIG. 11B shows luminance signals B1, B2, B for each lead 90 obtained by the horizontal scanning line signal SX.
3 is shown. N is 90 scratches on each lead
represents the noise signal caused by d.

FIG. 11C shows each of the luminance signals B1, B2.
The differential signal obtained by differentiating B3 is shown. At this time, the noise differential signal NC by the noise signal N is also detected.

In order to eliminate the influence of the noise differential signal NC due to the noise signal N in identifying the edge position of each lead, as shown in FIG. 11C, for example, when the differential signal is detected, the left end in the figure is detected. Actual left edge 9 of lead 90
Outside position D on the left of the position where 0L is predicted to exist
The differential signal of the luminance signal B1 is detected from L1 to the right, and the differential signal XL1 detected first is recognized as the differential signal by the left edge 90L.

Similarly, a process of detecting a differential signal of the luminance signal B1 from the outer position DR1 on the right side of the position where the actual right edge 90R of a certain lead 90 is predicted to exist to the left side is first detected. The differentiated signal XR1 is recognized as the differentiated signal by the right edge 90R.

In this manner, the left and right edge positions of the lead 90 are specified and the center position of the lead 90 is specified regardless of the noise differential signal NC due to the noise signal N formed at the center of the differential signal of the lead 90 (between XL1 and XR1). Can be calculated. The above-described differential signal detection processing is performed on each lead, the differential signals XL2 and XR2 of each lead, for example, in the center of the drawing are detected, the edge position is specified, and the lead center position is calculated.

By using the center position of each lead, for example, the center position of the leads or the center position of the whole lead can be obtained.

[0012]

At this time, in the image recognition of the lead portion of the electronic component, a detection line such as a scanning line is located at a position where the target lead is assumed to exist with respect to the image signal obtained by capturing the image of the electronic component. Then, the target lead portion position is calculated assuming that all the brightness change points of the white portion detected on the detection straight line are due to the lead.

Therefore, the reflection illumination is adjusted so that the portion other than the lead does not become a white portion on the detection straight line in the image signal, and the arrangement of the reflection illumination or the like is taken care so that the background of the electronic component to be recognized does not have a glowing portion. Had to do.

Further, in the case of a part in which a white part may occur other than the lead to be detected, it is necessary to set some assumptions or conditions for the image signal and select only the brightness change point by the target lead. is there. In this case, for example, if the shape of the part changes, the assumption and conditions of the lead detection line must be changed, and an image processing algorithm corresponding to the shape of the part is required each time. In particular, when leads and shining parts other than the leads are mixed, complicated assumptions and conditions are required, and there is a disadvantage that the change of the image processing algorithm becomes complicated.

In view of the above point, the present invention is capable of efficiently recognizing an electronic component having a shining portion other than the lead portion and a shining portion in the background of the electronic component to be recognized by a common algorithm. It is an object of the present invention to propose an image processing apparatus and a processing method that are resistant to irregularly shaped electronic components and noise on image signals.

[0016]

The image processing apparatus of the present invention comprises:
Image processing including image pickup means for picking up an image of an electronic component, model shape information storage means for storing model shape information of the electronic component, and image processing means for processing an image signal of the electronic component obtained by the image pickup means In the apparatus, the image processing means outputs model position information of a plurality of feature points regarding the electronic component of the model shape output from the model shape information storage means and position information of a plurality of feature point candidates obtained from the image signal. By comparing, the combination of the feature point candidates closest to the relative positional relationship of the feature points is selected, and the center position of the electronic component is calculated from the position information of the combination of the selected feature point candidates. . here,
The model position information of the characteristic points of this electronic component uses, for example, the central position coordinates of the plurality of reflecting portions to be detected when the electronic component is irradiated with light, and the position coordinates of the characteristic point candidates are, for example, The center position coordinates of a plurality of white parts when this image signal is binarized are used.

According to the present invention, the model position information of a plurality of feature points calculated from the model shape information of the electronic component is compared with the position information of the plurality of feature point candidates of the electronic component obtained from the image signal. Then, the combination of feature point candidates closest to the relative positional relationship of this feature point is selected, and the center position of the electronic component in this image signal is calculated from the position information of the selected combination of feature point candidates. Efficient unnecessary feature point candidates with a common algorithm even for electronic components where the lead part to be detected and the shining part other than the lead part are mixed, and even if there is a shining part in the background of the electronic part to be recognized The image signal can be recognized by removing the influence of, and image processing that is resistant to irregularly shaped electronic components and noise on the image signal can be performed.

Further, the image processing apparatus of the present invention selects, from the feature point candidates, a combination of two points which are estimated to correspond to the two points having the longest distance among the plurality of feature points. The image processing is performed by comparing the positions of this feature point and this feature point candidate only for the combination of feature point candidates including.

According to the present invention, some combinations of two points which are considered to correspond to the two points having the largest distance among the plurality of characteristic points are selected from the characteristic point candidates, and these two points are selected. Since the positions of the feature points and the feature point candidates are compared only for the combinations that include them, it is possible to avoid the brute force calculation in all cases and reduce the calculation time.

Further, the image processing apparatus of the present invention selects the two selected at the time of position comparison between the feature point and the feature point candidate.
For feature point candidates that include a combination of points, the combination of feature point candidates that do not have this white part near the position estimated from the model position information of this feature point is determined to be an incorrect combination, and the subsequent comparison calculation is performed. It was designed so that it would not exist.

According to the present invention, regarding a combination of two points selected from the characteristic point candidates, a combination in which a white portion does not exist near the position estimated from the model position information of the characteristic point is an incorrect combination. Since the determination is made and the subsequent comparison calculation is not performed, useless calculation can be avoided and calculation can be performed efficiently.

The image processing apparatus of the present invention is adapted to perform image processing by comparing the positions of the plurality of feature points and model feature point candidates using vectors.

According to the present invention, since the position comparison is performed using the vector, it is possible to easily perform the position comparison even for an electronic component having an arbitrary shape or an electronic component having an irregular shape.

According to the image processing method of the present invention, an image pickup means for picking up an image of an electronic part, a model shape information storage means for storing model shape information of the electronic part, and an image signal of the electronic part obtained by the image pickup means. In the image processing apparatus having image processing means for processing, the image processing means first obtains from the model position information of a plurality of feature points regarding the electronic component of the model shape output from the model shape information storage means and the image signal. Position information of a plurality of feature point candidates to be selected, next, a combination of the feature point candidates closest to the relative positional relationship of the feature points is selected, and position information of the combination of the selected feature point candidates is selected. The center position of this electronic component is calculated from. Here, the model position information of the characteristic points of this electronic component uses, for example, the central position coordinates of the plurality of detection target reflecting portions that are reflected when the electronic component is irradiated with light, and the position coordinates of the characteristic point candidates are used. Is one in which the center position coordinates of a plurality of white parts when this image signal is binarized are used.

Further, the image processing method of the present invention selects from the feature point candidates a combination of two points which are estimated to correspond to the two points having the largest distance among the plurality of feature points, and select these two points. The image processing is performed by comparing the positions of this feature point and this feature point candidate only for the combination of feature point candidates including.

In the image processing method of the present invention, the two points selected at the time of position comparison between the feature point and the feature point candidate are selected.
For feature point candidates that include a combination of points, the combination of feature point candidates that do not have this white part near the position estimated from the model position information of this feature point is determined to be an incorrect combination, and the subsequent comparison calculation is performed. It was designed so that it would not exist.

In the image processing method of the present invention, the positions of the plurality of feature points and the model feature point candidates are compared using vectors to perform image processing.

[0028]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of an image processing apparatus and a processing method according to the present invention will be described below with reference to the drawings.

FIG. 1 is a schematic configuration diagram showing an example of an electronic component mounter to which the image processing apparatus of the present invention is applied. This electronic component mounter is an electronic component (hereinafter,
A holding unit 2 for holding a "component") 1, and this holding unit 2
A driving device 3 for driving the device 1, an oblique reflection illumination 4 for irradiating the component 1 with light from an oblique position, a video camera 5 as an image pickup means for imaging the component 1, and an image signal from the video camera 5 temporarily. An image signal processing / control unit 6 for processing and controlling an image signal including an image memory unit 7a for storing, a calculation unit 7b, a model shape information storage device 8 and the like, and an image signal processing result in the image signal processing / control unit 6. Is composed of a communication means 9 for transmitting to the drive device 3.

In FIG. 1 configured as described above, the holding unit 2 driven by the drive unit 3 sucks and holds the component 1 by chuck means such as vacuum suction and holds and fixes the component 1 at a predetermined position in the air, for example. . The component 1 held in the air is irradiated with light from, for example, a position obliquely below the oblique reflection illumination 4 and also emitted from the coaxial reflection illumination 5b via the prism 5a.

The image of the component 1 irradiated with light is the prism 5a.
An image is captured by the video camera 5 via the. In the video camera 5, the image of the component 1 is converted into an image signal and sent to the image signal processing / control unit 6.

FIG. 2 shows an example of image signals of parts obtained by the video camera 5 and obtained on a monitor (not shown) or the like at this time.

Reference numeral 28 in the figure denotes a screen of a monitor or the like.
Is the image of the imaged part and 29 is the screen background. In the background 29, for example, a part of the holding portion 2 or the driving device 3 on the back side of the component 1 of the electronic component mounting machine should be reflected, but painting is performed on the holding portion 2 and the driving device 3 side so as to be imaged substantially black. Is being processed. Then, the three electrodes 11, 12, 1 are provided on one side of the substantially rectangular body portion of the component 10.
3 and two electrodes 14 and 15 on the side opposite to this, a total of 5
Since the light from the oblique reflection illumination 4 and the coaxial reflection illumination 5b is applied to the component 10 having a book electrode (hereinafter, referred to as "lead"), the light is reflected by the lead portion and appears white. The shaded body portion is a black mold, so that even if it is irradiated with light, the light does not reflect and appears almost black.

The image signal processing / control unit 6 processes the image signal from the video camera 5 and controls the drive unit 3 based on the processing result.

FIG. 3 shows an example in which the image signal of the component 10 shown in FIG. 2 is binarized by setting an appropriate threshold value for luminance.

By setting the threshold value to be larger than the luminance of the background 29 and the body portion of the black mold of the component and smaller than the luminance of the lead portions, the background 29 of the screen 28 becomes a black portion and the five leads 11, An image signal in which only 12, 13, 14, and 15 are white portions is obtained.

The image signal obtained from the video camera 5 is temporarily stored in the image memory section 7a, and at the same time, the calculation section 7b.
And the model shape information stored in the model shape information storage device 8 is compared with the part shape on the image signal by the calculation unit 7b.

The model shape information storage device 8 is composed of, for example, a ROM (Read Only Memory) or the like, and stores model shape information such as model position information of a plurality of feature points of a component.

Here, as a result of the above comparison, for example, the position of the component 1 on the image signal is greatly bent, or due to a lead defect or the like, the component 1 and the model of the component registered in the model shape information storage device 8 are obtained. When it is determined that the shape information is different from the shape information, the image processing step is not performed because the line process is rejected as a difference in the type of parts or a defective product.

When it is determined that the part 1 matches the model shape information, image processing described later is performed based on the model shape information, and the center position and angle of the part 1 are calculated.
Then, the calculated component center position and angle information is transmitted to the drive device 3 via the communication means 9.

In this drive unit 3, X based on the component center position and angle information supplied from the image signal processing / control unit 6 is used.
A position correction operation is performed in the three-dimensional directions of the YZ axes and the rotation direction r to set the component 1 to a predetermined position on, for example, a printed circuit board, and then the electrodes of the component 1 are subjected to soldering processing and the like. It is made to be mounted on a printed circuit board.

The image signals of the parts actually picked up by the video camera 5 are more complicated than those shown in FIGS. 2 and 3, and an example thereof is shown in FIG. In FIG. 4, parts corresponding to those in FIG. 2 are designated by the same reference numerals.

A total of five electrodes (hereinafter referred to as "leads"), that is, three electrodes 11, 12, and 13 on one side of the substantially rectangular body portion of the component 10 and two electrodes 14 and 15 on the opposite side. The light from the oblique reflection illumination 4 and the coaxial reflection illumination 5b is radiated to the component 10 having the above), so that the light is reflected on the lead portion and appears white. Since the body part of the component is a black mold, even if the light from these illuminations is applied, the light does not reflect and appears almost black.

Further, the screen background 29 also has white-reflected portions 16, 17, 24, 25, and the parts 10, 19, 20, 21, shining other than the lead portions on the component 10.
There are 22 and 23. Even if the threshold value is optimally selected by binarizing such an image signal, as shown in FIG.
The image has a white portion caused by other than the lead portion.

Here, the lead portion is represented as a quadrangular white portion and the other portions are represented as circular white portions, but there is no display distinction in the actual image signal.

Hereinafter, according to the flowchart showing the procedure of the image processing method of FIG. 6 and FIGS. 7 to 10, only the white portion caused by the lead portion of the part is arranged from the white portion arranged at an arbitrary position on the image signal. An algorithm for selecting and calculating the component center position and angle will be described.

First, model position information is created from the shape information of the parts (step 1).

Specifically, the center position coordinates of a plurality of reflecting portions to be detected among the reflecting portions that reflect light when the component is illuminated with reflected illumination are generated.

For example, for the component 10 shown in FIG. 2 which is arranged at a predetermined regular position, five leads 11, 1 are provided.
When it is desired to calculate the center position coordinates of the component by detecting 2, 13, 14, and 15, for example, model number information of the electronic component 10 is set in the image signal processing / control unit 6 by a setter (not shown) or the like. Then, the model shape information corresponding to the part 10 as shown in FIG. 7 is read from the model shape information storage device 8 and the model position information including the leads 31, 32, 33, 34, 35 is obtained. These leads are characteristic points that represent the shape of the component. Then, on the image signal, the center position coordinates (x1, y1) of each of these five leads,
(X2, y2), (x3, y3), (x4, y4),
(X5, y5) is calculated.

Next, the lead portion vector is calculated from this model position information (step 2).

First, one of the leads, which is the characteristic point of the model shape information of the component 10 shown in FIG. 7, is selected as a reference lead. The reference lead may be any lead, but it is preferable to select the lead at the end in order to improve the efficiency of calculation described later. For example, in the example of FIG. 7, the lead 31 located at the top among the leads at the right end is used as the reference lead.

Coordinates of the center position of the lead 31 (x1, y
The vector from 1) to the center of each lead is used as the lead portion vector and calculated for each lead. For example, in the example shown in FIG. 7, the vector from the lead 31 to the lead 32 is the lead portion vector 31a1.

Next, the longest read part vector is used as a reference vector. (Step 3)

In the example of FIG. 7, since the vector from the lead 31 to the lead 34 is the longest, it becomes the reference vector 31a.

Each vector calculated from the model position information of the model shape information of these parts 10 is registered in the model shape information storage device 8 in advance, and the center position of the part 10 to be described later is determined based on these vectors. As calculated.

Next, the image signal is binarized to calculate the center position of the white portion (step 4).

FIG. 8 shows an example of a binarized image obtained by binarizing the image signal of FIG. In practice, no distinction is made, but here, for the sake of explanation, the five lead portions to be detected are the white portions 11, 12, 13, 14, 15 having a square shape, and the other ones are
0 is round white part 16,17,18,19,20,2
Represented as 1, 22, 23, 24, 25. In addition, the respective white part center coordinates are (X1, Y1), (X2, Y
2), (X3, Y3), (X4, Y4), (X5, Y
5), (X6, Y6), (X7, Y7), (X8, Y
8), (X9, Y9), (X10, Y10), (X1
1, Y11), (X12, Y12) (X13, Y1
3), (X14, Y14), (X15, Y15).

Next, the reference vector is extended from each white part in the image to select a combination having a white part near the end point of the vector (step 5).

Specifically, the reference vector is extended with each white portion as the starting point, and some white portion exists within a certain range, for example, within the range of the reference vector length ± 10% and the angle ± 30 degrees. Select. The selected white portion located at the starting point of the reference vector is set as a reference lead candidate, and the vector from the white portion that is the reference lead candidate to the white portion within the above range is set as the reference vector candidate.

FIG. 9 shows coordinates (X3, Y3),
Three white parts 1 in (X2, Y2), (X1, Y1)
An example in which the reference vector 31a is extended from 3, 12, and 11 is shown. The reference vector length ± when the reference vector 31a is extended from each white part in the area indicated by the dotted line in the figure ±
The range is 10% and the angle is ± 30 degrees. It is determined whether or not it is a reference lead candidate by whether or not there is a white portion in this dotted line area.

For example, the white portion 13 of the coordinates (X3, Y3)
Is a reference lead candidate because the white portion 24 exists in the dotted line area when the reference vector 31a is extended. In the case of the white portion 12 at the coordinates (X2, Y2), the white portion does not exist in the dotted line area, so it is not a reference lead candidate. Further, in the case of the white portion 11 of the coordinates (X1, Y1), since there are two white portions 14 and 20 in the dotted line area, the white portion 11 serves as a reference lead candidate and has two reference vector candidates. In this way, one reference lead candidate may have a plurality of reference vector candidates.

Next, the squared error is obtained for each reference vector candidate (step 6).

First, a corrected lead portion vector is calculated by correcting the length and angle of the lead portion vector calculated in step 2 in accordance with the reference vector candidate. FIG. 10 shows an example of the reference vector candidate 13a extended from the white portion 13 which is a feature point candidate to the white portion 24 which is also a feature point candidate.

Of the model position information of the component 10, the lead and lead vectors for the leads 32 and 33 shown in FIG. 7 have their lengths and angles corrected according to the reference vector candidate 13a having the white portion 13 as a starting point. When the part vectors 31a1 'and 31a2' are calculated, the respective vector end points are set as the correction read part vector end points 32 'and 33'. For example, when the coordinates of the correction lead vector end point 32 'at this time are (x2', y2 '), and there is no positional deviation in the rotational direction with respect to the model component 10 shown in FIG. Can be calculated as

First, the correction lead portion vector end point 3
It is searched whether there is a white portion near 2 '(x2', y2 '). In the case of FIG. 10, since the white portion 17 is the closest white portion to this, the correction lead vector end point 32 '(x2
', Y2') and the square error between the white portion 17 (X7, Y7) are calculated, and this is added to the square error for the reference vector candidate 13a described above.

Next, similarly, the corrected lead portion vector end point 33 '(x3', y3 ') is obtained, and it is searched whether or not there is a white portion in this vicinity. When there is a white portion near the correction lead vector end point 33 ′, the squared error from the center position of the corresponding white portion is calculated and the reference vector candidate 13a is calculated as in the case of the correction lead vector end point 32 ′. Add to the squared error.

The above-described calculation is performed for all the read part vectors for the reference vector candidate to calculate the final squared error for the reference vector candidate.

By the way, in this example of FIG. 10, since there is no white portion near the correction lead portion vector end point 33 ', it is judged that the above-mentioned reference vector candidate 13a is not a reference vector, and the subsequent calculation is not performed. , And move to the calculation of the next reference vector candidate. Whether or not the white portion is present is determined, for example, by whether or not there is a white portion in the area (correction of the length and the angle error is set) of the correction lead vector end point 33 '.

As described above, the squared error calculation is performed for each reference vector candidate, the calculation of the squared error is not aborted in the middle, and the squared error is the most squared error among the reference vector candidates for which the squared error calculation is performed for all the lead part vectors. Is determined as the reference vector of the above-mentioned image signal component 10 (step 7).

Each white portion closest to the end point of each lead portion vector with respect to this reference vector is set as a white portion corresponding to the lead portion of the component 10, and the component position is again determined from the center position coordinates of this white portion by, for example, least square calculation. And the angle are calculated as the component center position and the component angle (step 8).

Then, the positional information such as the central position and the angle of the component 10 calculated through the above steps is sent to the drive unit 3 via the communication means 9 from the arithmetic unit 7b of the component mounter shown in FIG. If the electronic component 1 is transmitted and the position of the electronic component 1 is corrected, the electronic component 1 can be accurately mounted at a predetermined position such as a printed circuit board.

According to this example, the model position information of a plurality of feature points calculated from the model shape information of the electronic component is compared with the position information of a plurality of feature point candidates of the electronic component obtained from the image signal. Then, the combination of feature point candidates closest to the relative positional relationship of this feature point is selected, and the center position of the electronic component in this image signal is calculated from the position information of the selected combination of feature point candidates. Efficient unnecessary feature point candidates with a common algorithm even for electronic components where the lead part to be detected and the shining part other than the lead part are mixed, and even if there is a shining part in the background of the electronic part to be recognized The image signal can be recognized by removing the influence of, and image processing that is resistant to irregularly shaped electronic components and noise on the image signal can be performed. This eliminates the need to adjust the reflected illumination so that the parts other than the leads do not become white parts, and to be careful not to create a shining part in the background of the electronic component to be recognized, and to easily recognize various electronic components. it can.

Further, according to this example, some combinations of two points which are considered to correspond to the two points having the largest distance among the plurality of characteristic points are selected from the characteristic point candidates, and these two points are included. Since the positions of the characteristic points and the characteristic point candidates are compared only for the combinations, the calculation time can be shortened by avoiding the round-robin calculation in all cases.

Further, according to this example, regarding a combination of two points selected from the characteristic point candidates, a combination in which a white portion does not exist near the position estimated from the model position information of the characteristic point is determined to be an incorrect combination. However, since the subsequent comparison calculation is not performed, useless calculation can be avoided and calculation can be performed efficiently.

Further, according to the present example, since the position comparison is performed using the vector, it is possible to easily perform the position comparison for an electronic component having an arbitrary shape or an electronic component having an irregular shape.

It should be noted that the present invention is not limited to the examples of the above-described embodiments, and it goes without saying that various other configurations can be adopted without departing from the gist of the present invention.

[0077]

According to the present invention, even in an electronic component in which a lead portion to be detected and a shining portion other than the lead portion are mixed, and even when there is a shining portion in the background of the electronic component to be recognized. , The common algorithm can efficiently recognize the image signal by removing the influence of unnecessary feature point candidates, and has the advantage of being able to perform image processing that is robust against irregularly shaped electronic components and noise on the image signal. . This eliminates the need to adjust the reflected illumination so that the parts other than the leads do not become white parts, and to be careful not to create a shining part in the background of the electronic component to be recognized, and to easily recognize various electronic components. it can.

Further, according to the present invention, some combinations of two points which are considered to correspond to the two points having the largest distance among the plurality of characteristic points are selected from the characteristic point candidates, and the two points are selected.
When the positions of the feature points and the feature point candidates are compared only for combinations including points, there is an advantage that the calculation time can be shortened by avoiding brute force calculation in all cases.

Further, according to the present invention, regarding a combination of two points selected from the characteristic point candidates, a combination in which a white portion does not exist near the position estimated from the model position information of the characteristic point is determined as an incorrect combination. However, when the subsequent comparison calculation is not performed, there is an advantage that the calculation can be efficiently performed while avoiding useless calculation.

Further, according to the present invention, since the position comparison is performed using the vector, there is an advantage that the position comparison can be easily performed even for the electronic parts having an arbitrary shape and the electronic parts having an irregular shape. is there.

[Brief description of drawings]

FIG. 1 is a schematic configuration diagram showing an example of an embodiment of an image processing apparatus of the present invention.

FIG. 2 is a diagram showing an example of an image signal obtained from an electronic component.

FIG. 3 is a diagram showing an example of an image signal when the image signal of FIG. 2 is binarized.

FIG. 4 is a diagram showing an example of an image signal actually captured.

5 is a diagram showing an example of feature point candidates obtained by binarizing the image signal of FIG.

FIG. 6 is a flowchart showing the procedure of the image processing method of the present invention.

FIG. 7 is a diagram for explaining model position information calculation of an electronic component.

FIG. 8 is a diagram showing an example of center coordinates of a white portion of a binarized image signal.

FIG. 9 is a diagram for explaining calculation of reference vector candidates.

FIG. 10 is a diagram provided for explaining a squared error calculation for a reference vector candidate.

FIG. 11 is a diagram for explaining a conventional image processing method.

[Explanation of symbols]

1, 10 ... Electronic parts, 5 ... Video camera, 6 ... Image signal processing / control unit, 7a ... Image memory unit, 7b ...
Calculation unit, 8 ... Model shape information storage device, 11, 12,
13, 14, 15, 16, 17, 18, 19, 20, 2
1, 22, 23, 24, 25 ... White part (feature point candidate), 13a ... Reference vector candidate, 31, 32, 3
3, 34, 35 ...- Lead (feature point), 31a ...- Reference vector, 31a1 ...- Lead part vector, 31a1
', 31a2' ... Correction correction vector

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) H04N 7/18 H04N 7/18 WH H05K 13/04 H05K 13/04 MF term (reference) 2F065 AA17 CC25 FF04 HH12 HH13 JJ03 LL46 PP01 QQ24 QQ31 RR05 UU05 5B057 AA03 CA08 CA12 CB06 CB12 CE12 CH01 CH11 DA07 DB02 DB09 DC02 5C054 CA04 CC03 CD03 EA01 EA05 FC05 FC12 HA26 HAFF FF26 EE26FF24FF24FF24FF24EE24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24FF24EE24FF24FF24EE24FF24FF24FF24FF24EE24FF24FF23FF02FF24FF24FF24FF23FF23FF23 LA05

Claims (10)

[Claims] 1. An image pickup unit for picking up an image of an electronic component, a model shape information storage unit for storing model shape information of the electronic component, and an image processing unit for processing an image signal of the electronic component obtained by the image pickup unit. In the image processing device having the above, the image processing means is a plurality of feature point candidates obtained from model position information of a plurality of feature points related to an electronic component of a model shape output from the model shape information storage means and the image signal. So as to calculate the center position of the electronic component from the position information of the selected combination of feature point candidates, by selecting the combination of the feature point candidates closest to the relative positional relationship of the feature points. An image processing device characterized in that 2. The image processing apparatus according to claim 1, wherein the model position information of the characteristic points of the electronic component is a center of a plurality of reflecting portions which are reflection targets when the electronic component is irradiated with light. An image processing apparatus, wherein position coordinates are used, and as the position coordinates of the feature point candidates, center position coordinates of a plurality of white portions when the image signal is binarized are used. 3. The image processing apparatus according to claim 2, wherein a combination of two points estimated to correspond to the two points having the largest distance among the plurality of characteristic points is selected from the characteristic point candidates. An image processing apparatus, wherein the position of the feature point and the feature point candidate are compared and image processing is performed only for a combination of feature point candidates including the two points. 4. The image processing device according to claim 3, wherein at the time of position comparison between the feature point and the feature point candidate, a feature point candidate including a combination of the two selected points,
An image characterized in that a combination of feature point candidates in which the white portion does not exist near the position estimated from the model position information of the feature point is determined as an incorrect combination and the subsequent comparison calculation is not performed. Processing equipment. 5. The image processing apparatus according to claim 1, wherein the plurality of feature points and model feature point candidates are subjected to image processing by comparing positions using vectors. Image processing device. 6. An image pickup unit for picking up an image of an electronic component, a model shape information storage unit for storing model shape information of the electronic component, and an image processing unit for processing an image signal of the electronic component obtained by the image pickup unit. And the image processing means, first, the model position information of a plurality of feature points relating to the electronic component of the model shape output from the model shape information storage means and the position of a plurality of feature point candidates obtained from the image signal. Then, a combination of the feature point candidates closest to the relative positional relationship of the feature points is selected, and the center position of the electronic component is determined from the position information of the selected combination of feature point candidates. An image processing method characterized by being calculated. 7. The image processing method according to claim 6, wherein the model position information of the characteristic points of the electronic component is a center of a plurality of detection target reflection portions that are reflected when the electronic component is irradiated with light. An image processing method using position coordinates, wherein the position coordinates of the feature point candidates are center position coordinates of a plurality of white portions when the image signal is binarized. 8. The image processing method according to claim 7, wherein a combination of two points estimated to correspond to the two points having the largest distance among the plurality of characteristic points is selected from the characteristic point candidates. The image processing method is characterized in that the positions of the feature points and the feature point candidates are compared and image processing is performed only for a combination of feature point candidates including the two points. 9. The image processing method according to claim 8, wherein at the time of position comparison between the feature point and the feature point candidate, a feature point candidate including a combination of the two selected points,
An image characterized in that a combination of feature point candidates in which the white portion does not exist near the position estimated from the model position information of the feature point is determined as an incorrect combination and the subsequent comparison calculation is not performed. Processing method. 10. The image processing method according to claim 6, wherein for the plurality of feature points and model feature point candidates,
An image processing method characterized in that positions are compared using vectors to perform image processing.